Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to actions involving sending someone or something to a specific location or person

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.77
    orsi
    -0.66
    OWER
    -0.66
    ESS
    -0.63
    foundation
    -0.60
    kernel
    -0.59
    profit
    -0.59
     concession
    -0.58
     belief
    -0.58
    399
    -0.57
    POSITIVE LOGITS
    inel
    1.26
    entious
    1.00
    enced
    0.96
    keys
    0.88
    encing
    0.87
    opolis
    0.85
    books
    0.84
    imental
    0.82
    enc
    0.82
    iments
    0.81
    Act Density 0.022%

    No Known Activations